Multi-Descriptor Random Sampling for Patch-Based Face Recognition

While there has been a massive increase in research into face recognition, it remains challenging problem due to conditions present real life. This paper focuses on the inherently issue of partial occlusion distortions recognition applications. We propose an approach tackle this problem. First, images are divided multiple patches before local descriptors Local Binary Patterns and Histograms Oriented Gradients applied each patch. Next, resulting histograms concatenated, their dimensionality is then reduced using Kernel Principle Component Analysis. Once completed, randomly selected concept random sampling finally construct several sub-Support Vector Machine classifiers. The results obtained from these sub-classifiers combined generate final outcome. Experimental based AR database Extended Yale B show effectiveness our proposed technique.